Search Results for "commons-collections"

Unsupervised Machine Translation is a research repository that implements both phrase-based SMT and neural MT approaches for translation without parallel corpora. The neural component supports multiple architectures—seq2seq, biLSTM with attention, and Transformer—and allows extensive parameter sharing across languages to improve data efficiency. Training relies on denoising auto-encoding and back-translation, with on-the-fly, multithreaded generation of synthetic parallel data to continually...

CompE Toolkit allows the user to seamlessly convert between binary, decimal, hexadecimal, and 32-bit floating point representation. It uses a simple, user-friendly interface designed for maximum efficiency and minimal clutter.

TextTools is a freeware corpus linguistics tool developed in Python to aid in research. This program analyzes user-created corpora and displays information about word (token) frequency, n-grams, clusters, collocations, keyword in context (KWIC), and keyness. TextTools is designed to be user-friendly and intuitive and will run natively on Mac OS X.

The central problem to be addressed in this project concerns a multidisciplinary (linguistics and computational linguistics) investigation into sharing of knowledge and resources between closely-related languages, specifically relating to the automatic processing of compounds. Specifically, we will explore the possibility to create new knowledge about closely-related languages, and efficiently develop additional, more advanced resources for (a) compound segmentation; and (b) the semantic...